Migrate to pytest and expand test coverage

.github/workflows/test-workflow.yml

@@ -0,0 +1,75 @@
+name: Run Tests
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:  # Allow manual trigger
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+      fail-fast: false  # Continue other versions if one fails
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+        cache: 'pip'  # Cache pip dependencies
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+        pip install pytest pytest-cov pytest-mock requests-mock
+
+    - name: Run unit tests
+      run: |
+        pytest -v -m "unit" --cov=. --cov-report=term-missing --cov-report=xml
+      env:
+        PYTHONPATH: ${{ github.workspace }}
+
+    - name: Run integration tests
+      run: |
+        pytest -v -m "integration" --cov=. --cov-append --cov-report=term-missing --cov-report=xml
+      env:
+        PYTHONPATH: ${{ github.workspace }}
+
+    - name: Run API tests
+      run: |
+        pytest -v -m "api" --cov=. --cov-append --cov-report=term-missing --cov-report=xml
+      env:
+        PYTHONPATH: ${{ github.workspace }}
+
+    - name: Run all unmarked tests
+      run: |
+        pytest -v -m "not slow" --cov=. --cov-append --cov-report=term-missing --cov-report=xml
+      env:
+        PYTHONPATH: ${{ github.workspace }}
+
+    - name: Generate coverage report
+      if: always()
+      run: |
+        python -m pip install coverage
+        coverage report --show-missing || true
+
+    - name: Upload coverage artifact
+      if: matrix.python-version == '3.10'
+      uses: actions/upload-artifact@v4
+      with:
+        name: coverage-report
+        path: |
+          coverage.xml
+          htmlcov/
+        retention-days: 30

.gitignore

@@ -3,6 +3,11 @@ ___pycache__
 *.pyc
 .DS_Store
 
+# Test coverage
+.coverage
+htmlcov/
+.pytest_cache/
+
 # Ignore output files
 logs/
 output/

pyproject.toml

@@ -0,0 +1,73 @@
+[build-system]
+requires = ["setuptools>=45", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sfs-processor"
+version = "0.1.0"
+description = "Swedish legal document processor"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "requests>=2.25.0",
+    "pyyaml>=6.0",
+    "markdown>=3.4.0",
+]
+
+[project.optional-dependencies]
+test = [
+    "pytest>=7.4.0",
+    "pytest-cov>=4.1.0",
+    "pytest-mock>=3.12.0",
+    "requests-mock>=1.11.0",
+]
+
+[tool.pytest.ini_options]
+# Test discovery
+testpaths = ["test"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+
+# Output options
+addopts = [
+    "-v",                          # Verbose output
+    "--tb=short",                  # Shorter traceback format
+    "--strict-markers",            # Error on unknown markers
+    "--color=yes",                 # Colored output
+    "-ra",                         # Show summary of all test outcomes
+    "--cov=.",                     # Coverage for all modules
+    "--cov-report=term-missing",   # Show missing lines in coverage
+    "--cov-report=html:htmlcov",   # HTML coverage report
+    "--cov-branch",                # Branch coverage
+]
+
+# Markers for test categorization
+markers = [
+    "unit: Unit tests that don't require external resources",
+    "integration: Integration tests that test multiple components",
+    "api: Tests that interact with external APIs (mocked)",
+    "slow: Tests that take significant time to run",
+]
+
+# Coverage settings
+[tool.coverage.run]
+source = ["."]
+omit = [
+    "test/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/site-packages/*",
+    ".venv/*",
+    "venv/*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+]

test/conftest.py

@@ -0,0 +1,128 @@
+"""
+Shared pytest fixtures and configuration for sfs-processor tests.
+"""
+import pytest
+from pathlib import Path
+
+
+@pytest.fixture
+def project_root():
+    """Return the project root directory."""
+    return Path(__file__).parent.parent
+
+
+@pytest.fixture
+def test_data_dir(project_root):
+    """Return the test data directory."""
+    return project_root / "test" / "data"
+
+
+@pytest.fixture
+def sample_temporal_title():
+    """Sample temporal title with date markers for testing."""
+    return """/Rubriken upphör att gälla U:2025-07-15/
+Förordning (2023:30) om statsbidrag till regioner för åtgärder för att höja driftsäkerheten på hälso- och sjukvårdens fastigheter
+/Rubriken träder i kraft I:2025-07-15/
+Förordning om statsbidrag till regioner för åtgärder för att höja driftsäkerheten på fastigheter för hälso- och sjukvård"""
+
+
+@pytest.fixture
+def sample_sfs_document():
+    """Sample SFS document data for testing."""
+    return {
+        'beteckning': '2023:30',
+        'rubrik': """/Rubriken upphör att gälla U:2025-07-15/
+Förordning (2023:30) om statsbidrag till regioner för åtgärder för att höja driftsäkerheten på hälso- och sjukvårdens fastigheter
+/Rubriken träder i kraft I:2025-07-15/
+Förordning om statsbidrag till regioner för åtgärder för att höja driftsäkerheten på fastigheter för hälso- och sjukvård""",
+        'fulltext': {
+            'innehall': 'Test innehåll här...'
+        }
+    }
+
+
+@pytest.fixture
+def mock_riksdagen_responses(requests_mock):
+    """
+    Mock common Riksdagen API responses.
+    Can be customized per test by accessing the requests_mock fixture.
+    """
+    # Mock successful proposition (prop 2024/25:1 -> HB031)
+    requests_mock.get(
+        'https://data.riksdagen.se/dokument/HB031.json',
+        json={
+            'dokumentstatus': {
+                'dokument': {
+                    'dokumentnamn': 'Prop. 2024/25:1',
+                    'titel': 'Budgetpropositionen för 2025',
+                    'rm': '2024/25',
+                    'beteckning': '1',
+                    'typ': 'prop',
+                    'dokument_url_html': 'https://data.riksdagen.se/dokument/HB031.html'
+                }
+            }
+        }
+    )
+
+    # Mock successful proposition (prop 2023/24:144 -> HA03144)
+    requests_mock.get(
+        'https://data.riksdagen.se/dokument/HA03144.json',
+        json={
+            'dokumentstatus': {
+                'dokument': {
+                    'dokumentnamn': 'Prop. 2023/24:144',
+                    'titel': 'Test proposition',
+                    'rm': '2023/24',
+                    'beteckning': '144',
+                    'typ': 'prop',
+                    'dokument_url_html': 'https://data.riksdagen.se/dokument/HA03144.html'
+                }
+            }
+        }
+    )
+
+    # Mock successful bet (committee report) (bet 2023/24:JuU3 -> HA01JuU3)
+    requests_mock.get(
+        'https://data.riksdagen.se/dokument/HA01JuU3.json',
+        json={
+            'dokumentstatus': {
+                'dokument': {
+                    'dokumentnamn': 'Bet. 2023/24:JuU3',
+                    'titel': 'Justitieutskottets betänkande',
+                    'rm': '2023/24',
+                    'beteckning': 'JuU3',
+                    'typ': 'bet',
+                    'dokument_url_html': 'https://data.riksdagen.se/dokument/HA01JuU3.html'
+                }
+            }
+        }
+    )
+
+    # Mock riksdagsskrivelse (rskr 2023/24:9 -> HA049)
+    requests_mock.get(
+        'https://data.riksdagen.se/dokument/HA049.json',
+        json={
+            'dokumentstatus': {
+                'dokument': {
+                    'dokumentnamn': 'Rskr. 2023/24:9',
+                    'titel': 'Riksdagens skrivelse',
+                    'rm': '2023/24',
+                    'beteckning': '9',
+                    'typ': 'rskr',
+                    'dokument_url_html': 'https://data.riksdagen.se/dokument/HA049.html'
+                }
+            }
+        }
+    )
+
+    return requests_mock
+
+
+@pytest.fixture
+def mock_riksdagen_404(requests_mock):
+    """Mock a 404 response from Riksdagen API."""
+    requests_mock.get(
+        'https://data.riksdagen.se/dokument/G60340.json',
+        status_code=404
+    )
+    return requests_mock